这里直接贴出代码实现,说实话我也没弄懂MD5具体原理,我们只要知道怎么使用即可。我是用的是C语言,在vs2010上实现的。
MD5算法代码
md5.h:最终我们只需要调用三个函数即可完成对MD5值的计算
#ifndef MD5_H
#define MD5_H
#include<string.h>
#include<stdio.h>
#include<stdlib.h>
typedef unsigned int u32;
typedef unsigned char u8;
typedef struct
{
u32 state[4]; //A,B,C,D四个常数
u32 count[2]; //数据bit数计数器,总共有64bit也就是两个u32
u8 buffer[64]; //输入数据缓存区,每一轮计算都是将512位的数据进行分组也就是64个u8
}MD5_CTX;
//循环左移的位数
//第一轮
#define S11 7
#define S12 12
#define S13 17
#define S14 22
//第2轮
#define S21 5
#define S22 9
#define S23 14
#define S24 20
//第3轮
#define S31 4
#define S32 11
#define S33 16
#define S34 23
//第4轮
#define S41 6
#define S42 10
#define S43 15
#define S44 21
//F, G, H, I四个非线性变换函数
#define F(x,y,z) ((x & y) | (~x & z))
#define G(x,y,z) ((x & z) | (y & ~z))
#define H(x,y,z) (x^y^z)
#define I(x,y,z) (y ^ (x | ~z))
//x循环左移n位的操作
#define ROTATE_LEFT(x,n) ((x << n) | (x >> (32-n)))
//FF, GG, HH, II是四轮循环变换分别用到的变换函数
#define FF(a, b, c, d, x, s, ac) { \
(a) += F ((b), (c), (d)) + (x) + (unsigned int)(ac); \
(a) = ROTATE_LEFT ((a), (s)); \
(a) += (b); \
}
#define GG(a, b, c, d, x, s, ac) { \
(a) += G ((b), (c), (d)) + (x) + (unsigned int)(ac); \
(a) = ROTATE_LEFT ((a), (s)); \
(a) += (b); \
}
#define HH(a, b, c, d, x, s, ac) { \
(a) += H ((b), (c), (d)) + (x) + (unsigned int)(ac); \
(a) = ROTATE_LEFT ((a), (s)); \
(a) += (b); \
}
#define II(a, b, c, d, x, s, ac) { \
(a) += I ((b), (c), (d)) + (x) + (unsigned int)(ac); \
(a) = ROTATE_LEFT ((a), (s)); \
(a) += (b); \
}
void MD5Init (MD5_CTX *);
void MD5Update(MD5_CTX *, unsigned char *, unsigned int);
void MD5Final(unsigned char [16], MD5_CTX *);
#endif
md5.c:这里主要是具体的代码实现
#include <memory.h>
#include "md5.h"
//数据填充的内容
unsigned char PADDING[64] = {
0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
};
//将无符号整数转为字节类型数组
static void Encode (unsigned char *output, unsigned int *input,unsigned int len)
{
unsigned int i, j;
for (i = 0, j = 0; j < len; i++, j += 4)
{
output[j] = (unsigned char)(input[i] & 0xff);
output[j+1] = (unsigned char)((input[i] >> 8) & 0xff);
output[j+2] = (unsigned char)((input[i] >> 16) & 0xff);
output[j+3] = (unsigned char)((input[i] >> 24) & 0xff);
}
}
//将字节类型数组转为无符号整数
static void Decode (unsigned int *output, unsigned char *input, unsigned int len)
{
unsigned int i, j;
for (i = 0, j = 0; j < len; i++, j += 4)
output[i] = ((unsigned int)input[j]) | (((unsigned int)input[j+1]) << 8) |
(((unsigned int)input[j+2]) << 16) | (((unsigned int)input[j+3]) << 24);
}
//MD5变换函数
static void MD5Transform (unsigned int state[4], unsigned char block[64])
{
unsigned int a = state[0], b = state[1], c = state[2], d = state[3], x[16];
//将64字节的一组数据进一步划分为16个子分组
Decode (x, block, 64);
//第1轮循环变换
FF (a, b, c, d, x[ 0], S11, 0xd76aa478); /* 1 */
FF (d, a, b, c, x[ 1], S12, 0xe8c7b756); /* 2 */
FF (c, d, a, b, x[ 2], S13, 0x242070db); /* 3 */
FF (b, c, d, a, x[ 3], S14, 0xc1bdceee); /* 4 */
FF (a, b, c, d, x[ 4], S11, 0xf57c0faf); /* 5 */
FF (d, a, b, c, x[ 5], S12, 0x4787c62a); /* 6 */
FF (c, d, a, b, x[ 6], S13, 0xa8304613); /* 7 */
FF (b, c, d, a, x[ 7], S14, 0xfd469501); /* 8 */
FF (a, b, c, d, x[ 8], S11, 0x698098d8); /* 9 */
FF (d, a, b, c, x[ 9], S12, 0x8b44f7af); /* 10 */
FF (c, d, a, b, x[10], S13, 0xffff5bb1); /* 11 */
FF (b, c, d, a, x[11], S14, 0x895cd7be); /* 12 */
FF (a, b, c, d, x[12], S11, 0x6b901122); /* 13 */
FF (d, a, b, c, x[13], S12, 0xfd987193); /* 14 */
FF (c, d, a, b, x[14], S13, 0xa679438e); /* 15 */
FF (b, c, d, a, x[15], S14, 0x49b40821); /* 16 */
//第2轮循环变换
GG (a, b, c, d, x[ 1], S21, 0xf61e2562); /* 17 */
GG (d, a, b, c, x[ 6], S22, 0xc040b340); /* 18 */
GG (c, d, a, b, x[11], S23, 0x265e5a51); /* 19 */
GG (b, c, d, a, x[ 0], S24, 0xe9b6c7aa); /* 20 */
GG (a, b, c, d, x[ 5], S21, 0xd62f105d); /* 21 */
GG (d, a, b, c, x[10], S22, 0x2441453); /* 22 */
GG (c, d, a, b, x[15], S23, 0xd8a1e681); /* 23 */
GG (b, c, d, a, x[ 4], S24, 0xe7d3fbc8); /* 24 */
GG (a, b, c, d, x[ 9], S21, 0x21e1cde6); /* 25 */
GG (d, a, b, c, x[14], S22, 0xc33707d6); /* 26 */
GG (c, d, a, b, x[ 3], S23, 0xf4d50d87); /* 27 */
GG (b, c, d, a, x[ 8], S24, 0x455a14ed); /* 28 */
GG (a, b, c, d, x[13], S21, 0xa9e3e905); /* 29 */
GG (d, a, b, c, x[ 2], S22, 0xfcefa3f8); /* 30 */
GG (c, d, a, b, x[ 7], S23, 0x676f02d9); /* 31 */
GG (b, c, d, a, x[12], S24, 0x8d2a4c8a); /* 32 */
//第3轮循环变换
HH (a, b, c, d, x[ 5], S31, 0xfffa3942); /* 33 */
HH (d, a, b, c, x[ 8], S32, 0x8771f681); /* 34 */
HH (c, d, a, b, x[11], S33, 0x6d9d6122); /* 35 */
HH (b, c, d, a, x[14], S34, 0xfde5380c); /* 36 */
HH (a, b, c, d, x[ 1], S31, 0xa4beea44); /* 37 */
HH (d, a, b, c, x[ 4], S32, 0x4bdecfa9); /* 38 */
HH (c, d, a, b, x[ 7], S33, 0xf6bb4b60); /* 39 */
HH (b, c, d, a, x[10], S34, 0xbebfbc70); /* 40 */
HH (a, b, c, d, x[13], S31, 0x289b7ec6); /* 41 */
HH (d, a, b, c, x[ 0], S32, 0xeaa127fa); /* 42 */
HH (c, d, a, b, x[ 3], S33, 0xd4ef3085); /* 43 */
HH (b, c, d, a, x[ 6], S34, 0x4881d05); /* 44 */
HH (a, b, c, d, x[ 9], S31, 0xd9d4d039); /* 45 */
HH (d, a, b, c, x[12], S32, 0xe6db99e5); /* 46 */
HH (c, d, a, b, x[15], S33, 0x1fa27cf8); /* 47 */
HH (b, c, d, a, x[ 2], S34, 0xc4ac5665); /* 48 */
//第4轮循环变换
II (a, b, c, d, x[ 0], S41, 0xf4292244); /* 49 */
II (d, a, b, c, x[ 7], S42, 0x432aff97); /* 50 */
II (c, d, a, b, x[14], S43, 0xab9423a7); /* 51 */
II (b, c, d, a, x[ 5], S44, 0xfc93a039); /* 52 */
II (a, b, c, d, x[12], S41, 0x655b59c3); /* 53 */
II (d, a, b, c, x[ 3], S42, 0x8f0ccc92); /* 54 */
II (c, d, a, b, x[10], S43, 0xffeff47d); /* 55 */
II (b, c, d, a, x[ 1], S44, 0x85845dd1); /* 56 */
II (a, b, c, d, x[ 8], S41, 0x6fa87e4f); /* 57 */
II (d, a, b, c, x[15], S42, 0xfe2ce6e0); /* 58 */
II (c, d, a, b, x[ 6], S43, 0xa3014314); /* 59 */
II (b, c, d, a, x[13], S44, 0x4e0811a1); /* 60 */
II (a, b, c, d, x[ 4], S41, 0xf7537e82); /* 61 */
II (d, a, b, c, x[11], S42, 0xbd3af235); /* 62 */
II (c, d, a, b, x[ 2], S43, 0x2ad7d2bb); /* 63 */
II (b, c, d, a, x[ 9], S44, 0xeb86d391); /* 64 */
state[0] += a;
state[1] += b;
state[2] += c;
state[3] += d;
}
//MD5算法初始化操作
void MD5Init (MD5_CTX *context)
{
//bit计数器清零
context->count[0] = context->count[1] = 0;
//A,B,C,D被初始化为四个特定的常数(Magic Number)
context->state[0] = 0x67452301;
context->state[1] = 0xefcdab89;
context->state[2] = 0x98badcfe;
context->state[3] = 0x10325476;
}
//使用MD5算法对input的数据进行处理
void MD5Update (MD5_CTX *context, unsigned char *input, unsigned int inputLen)
{
unsigned int i, index, partLen;
//计算[已处理数据长度(byte) mod 64]
index = (unsigned int)((context->count[0] >> 3) & 0x3F);
//计算缓冲区还有多少字节空间
partLen = 64 - index;
//bit计数器累加
if ((context->count[0] += ((unsigned int)inputLen << 3)) < ((unsigned int)inputLen << 3)) //处理加法进位溢出的情况
{
context->count[1]++;
}
context->count[1] += ((unsigned int)inputLen >> 29);
//以512位数据为一组进行处理
if (inputLen >= partLen)
{
memcpy(&context->buffer[index],input, partLen);
MD5Transform (context->state, context->buffer);
for (i = partLen; i + 63 < inputLen; i += 64)
{
MD5Transform (context->state, &input[i]);
}
index = 0;
}
else
{
i = 0;
}
//缓存未处理的输入
memcpy(&context->buffer[index],&input[i],inputLen-i);
}
//获取MD5码(由digest返回),顺便清除context数据
void MD5Final (unsigned char digest[16], MD5_CTX *context)
{
unsigned char bits[8];
unsigned int index, padLen;
//填充数据
index = (unsigned int)((context->count[0] >> 3) & 0x3f);
padLen = (index < 56) ? (56 - index) : (120 - index);
//记录数据长度
Encode (bits, context->count, 8);
MD5Update (context, PADDING, padLen);
//追加数据长度信息
MD5Update (context, bits, 8);
//获取MD5码。其实就是将ABCD四个32位整数以16进制方式级联
Encode (digest, context->state, 16);
//清除数据
memset(context, 0, sizeof(*context));
}
文件操作
由于涉及到对文件的读取,我们这里需要对文件操作。 MD5计算需要两中数据:文件大小和文件内容。我们知道所有的文件存储在计算机中都是以二进制形式存储的,这样我们就能够计算任意格式文件的MD5。
事实上,你在网上下载的任意一个MD5计算工具,他们也是将文件以二进制文件读出,然后实现MD5计算。
#ifndef FILE_H
#define FILE_H
#include<stdio.h>
#include<stdlib.h>
long long getFileSize(char * files);
char* copyFile(char * sourceFile, long long* file_size);
#endif
#include "file.h"
/*
功能:获取文件大小
note:这里是以二进制的格式读取文件,因此可以读取任意格式的文件
*/
long long getFileSize(char * files)
{
long long size;
fpos_t pos;//定义文件位置pos
FILE *fp = fopen(files,"rb+");//以二进制读形式打开文件
if( fp == NULL){
printf("Open File Error");
exit(0);
}
//获取文件指针(指向文件开头),写入pos
fgetpos(fp,&pos);
//文件指针指向末尾
fseek(fp,0,SEEK_END);
//获取文件指针到文件头部的字节大小
size = ftell(fp);
//文件指针还原
fsetpos(fp,&pos);
//释放文件
fclose(fp);
printf("文件大小:%d\n", size);
return size;
}
/*
功能:以二进制格式将文件内容读出到缓存中
*/
char* copyFile(char * sourceFile, long long* file_size)
{
char * buffer = NULL;
//打开文件
FILE *fpSource = fopen(sourceFile,"rb+");
if( fpSource == NULL)
{
printf("Open File Error...");
exit(1);
}
//获取文件大小
*file_size = getFileSize(sourceFile);
//在堆区申请和文件大小一致的缓存用来存储读到的数据
buffer = (char *) malloc(*file_size);
fread(buffer,1,*file_size,fpSource);
fclose(fpSource);
return buffer;
}
测试代码
在main.c中,有三段测试代码,可以打开不同的宏,来测试不同的功能
#include"md5.h"
#include"file.h"
int main()
{
#if 0//计算字符串MD5
MD5_CTX md5_calc;
int i;
char c[]="abc";
unsigned char md5[16];
//演示计算字符串abc的MD5码
MD5Init(&md5_calc);
MD5Update(&md5_calc,(unsigned char *)c,strlen(c));
MD5Final(md5,&md5_calc);
//输出MD5码
printf("字符串abc的MD5码为:");
for(i=0;i<16;i++) printf("%02x",md5[i]);
printf("\n");
#endif
#if 0//计算文件大小
char path[300];
MD5_CTX md5_calc;
int i;
unsigned char md5[16];
printf("请输入文件路径:\n");
gets(path);
printf("文件大小为:%d\n",getFileSize(path));
#endif
#if 1//计算文件MD5
MD5_CTX md5_calc;
int i;
unsigned char md5[16];
char path[300];
long long file_size = 0;
char* data_buffer = NULL;
printf("请输入文件路径:\n");
gets(path);
data_buffer = copyFile(path, &file_size);
MD5Init(&md5_calc);
MD5Update(&md5_calc, (unsigned char *)data_buffer, file_size);
MD5Final(md5,&md5_calc);
//输出MD5码
printf("文件的MD5码为:");
for(i=0;i<16;i++)
{
printf("%02x",md5[i]);
}
printf("\n");
#endif
system("pause");
return 0;
}
简单测试了一下文件计算值
我们右键查看文件属性,可以看到文件大小4923和读到的文件大小是一致的。